Search Results for author:
Found 23 papers, 13 papers with code
Talking Point based Ideological Discourse Analysis in News Events
Analyzing ideological discourse even in the age of LLMs remains a challenge, as these models often struggle to capture the key elements that shape real-world narratives.
$\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
Recent studies show the growing significance of document retrieval in the generation of LLMs, i. e., RAG, within the scientific domain by bridging their knowledge gap.
Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness
In this work, we study whether retrievers can recognize and respond to different perspectives of the queries -- beyond finding relevant documents for a claim, can retrievers distinguish supporting vs. opposing documents?
Minimal Evidence Group Identification for Claim Verification
Claim verification in real-world settings (e. g. against a large collection of candidate evidences retrieved from the web) typically requires identifying and aggregating a complete set of evidence pieces that collectively provide full support to the claim.
Conceptual and Unbiased Reasoning in Language Models
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition.
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research.
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
The Trickle-down Impact of Reward (In-)consistency on RLHF
We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM.
ExpertQA: Expert-Curated Questions and Attributed Answers
In this work, we conduct human evaluation of responses from a few representative systems along various axes of attribution and factuality, by bringing domain experts in the loop.
Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
We propose the Dynamic Clue Bottleneck Model ( (DCLUB), a method that is designed towards an inherently interpretable VQA system.
Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Start
To facilitate research in this domain, we propose and study a conceptual framework, where we compare how sources typically mention certain controversial entities, and use such as indicators for the sources' content selection preferences.
PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
As these propositions can carry different truth values in the context of a given premise, we argue for the need to recognize the textual entailment relation of each proposition in a sentence individually.
Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters
Natural Language Inference (NLI) has been extensively studied by the NLP community as a framework for estimating the semantic relation between sentence pairs.
Image Reconstruction for MRI using Deep CNN Priors Trained without Groundtruth
We propose a new plug-and-play priors (PnP) based MR image reconstruction method that systematically enforces data consistency while also exploiting deep-learning priors.
Design Challenges for a Multi-Perspective Search Engine
Naturally, identifying such responses within a document is a natural language understanding task.
MultiOpEd: A Corpus of Multi-Perspective News Editorials
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery.
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context.
Evaluating NLP Models via Contrast Sets
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
Evaluating Models' Local Decision Boundaries via Contrast Sets
Unfortunately, when a dataset has systematic gaps (e. g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities.
PerspectroScope: A Window to the World of Diverse Perspectives
This work presents PerspectroScope, a web-based system which lets users query a discussion-worthy natural language claim, and extract and visualize various perspectives in support or against the claim, along with evidence supporting each perspective.
Natural Language Inference
Natural Language Understanding
+1
Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
Inherently, this is a natural language understanding task, and we propose to address it as such.
Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims
Inherently, this is a natural language understanding task, and we propose to address it as such.
